Digital Microscopy Augmented by Artificial Intelligence to Interpret Bone Marrow Samples for Hematological Diseases.

Analysis of bone marrow aspirates (BMAs) is an essential step in the diagnosis of hematological disorders. This analysis is usually performed based on a visual examination of samples under a conventional optical microscope, which involves a labor-intensive process, limited by clinical experience and subject to high observer variability. In this work, we present a comprehensive digital microscopy system that enables BMA analysis for cell type counting and differentiation in an efficient and objective manner. This system not only provides an accessible and simple method to digitize, store, and analyze BMA samples remotely but is also supported by an Artificial Intelligence (AI) pipeline that accelerates the differential cell counting process and reduces interobserver variability. It has been designed to integrate AI algorithms with the daily clinical routine and can be used in any regular hospital workflow.

Multidisciplinary management in chronic myeloid leukemia improves cardiovascular risk measured by SCORE.

Introduction: Cardiovascular events are one of the main long-term complications in patients with chronic myeloid leukemia (CML) receiving treatment with tyrosine kinase inhibitors (TKIs). The proper choice of TKI and the adequate management of risk factors may reduce cardiovascular comorbidity in this population. Methods: This study evaluated the cardiovascular risk of a cohort of patients with CML at diagnosis and after follow-up in a specialized cardiovascular risk consultation. In order to do this, we performed data analysis from 35 patients who received TKIs and were referred to the aforementioned consultation between 2015 and 2018 at our center. Cardiovascular risk factors were analyzed separately, as well as integrated into the cardiovascular SCORE, both at diagnosis and at the last visit to the specialized consultation. Results: At the time of diagnosis, 60% had some type of risk factor, 20% had a high or very high risk SCORE, 40% had an intermediate risk, and 40% belonged to the low risk category. During follow-up, the main cardiovascular adverse event observed was hypertension (diagnosed in 8 patients, 23%). 66% of patients quit smoking, achieving control of blood pressure in 95%, diabetes in 50%, weight in 76%, and dyslipidemia in 92%. 5.7% of patients suffered a thrombotic event and a significant percentage of patients showed a reduction in their SCORE. Conclusion: Our study shows the benefit of controlling cardiovascular risk factors through follow-up in a specialized consultation for patients with CML treated with TKI.

[Evaluation of pathological response to neoadjuvant chemotherapy in breast cancer: correlation with molecular phenotype]. / Evaluación de la respuesta patológica a quimioterapia neoadyuvante en cáncer de mama: correlación con el fenotipo molecular.

INTRODUCTION AND OBJECTIVE: Breast cancer can be classified into different molecular subtypes with important therapeutic and prognostic implications. Neoadjuvant chemotherapy (NAC) increases the possibility of performing conservative surgery and allows in vivo testing of the sensitivity of the tumor. Our aim was to evaluate the pathological response to NAC in relation to the molecular phenotype and the different definitions of the pathological response. PATIENTS: 228 patients treated with NAC and subsequent surgery between 2012 and 2018 were selected from our breast cancer database. Molecular phenotypes were established based on the criteria of the St Gallen 2013 Conference. Pathological response was evaluated following Miller-Payne (breast) and Sataloff (axilla) classification systems. RESULTS: The most frequent molecular phenotype was luminal B/HER2 negative (30.3%), followed by luminal B/HER2 positive (26.3%), triple negative (24.6%), HER2 positive (13.2%), and luminal A (5.7%). The rate of pathological complete response (pCR) was 35.5% in breast and 15.3% in axilla. The rate of pCR considering breast and axilla together was 26.8%. The molecular phenotype with the highest rate of pCR was HER2 positive (66.7%) followed by triple negative (30.4%), luminal B/HER2 positive (21.7%), luminal B/HER2 negative (14.5%), and luminal A (7.7%) (p < 0.001). The same results were found with the different definitions of pCR we evaluated. CONCLUSIONS: Complete pathological response to NAC in breast cancer depends largely on the molecular phenotype of the tumor, regardless of the definition of pCR, with the highest response rates in the breast and axilla in the HER2 positive and triple negative phenotypes.